Gastric cancer (GC) is one of the leading causes of cancer-related death worldwide. It takes some time from chronic gastritis to develop in GC. Early detection of GC will help patients obtain timely treatment. Understanding disease evolution is crucial for the prevention and treatment of GC. Here, we present a convolutional neural network (CNN)-based system to detect abnormalities in the gastric mucosa. We identified normal mucosa, chronic gastritis, and intestinal-type GC: this is the most common route of gastric carcinogenesis. We integrated digitalizing histopathology of whole-slide images (WSIs), stain normalization, a deep CNN, and a random forest classifier. The staining variability of WSIs was reduced significantly through stain normalization, and saved the cost and time of preparing new slides. Stain normalization improved the effect of the CNN model. The accuracy rate at the patch-level reached 98.4%, and 94.5% for discriminating normal → chronic gastritis → GC. The accuracy rate at the WSIs-level for discriminating normal tissue and cancerous tissue reached 96.0%, which is a state-of-the-art result. Survival analyses indicated that the features extracted from the CNN exerted a significant impact on predicting the survival of cancer patients. Our CNN model disclosed significant potential for adjuvant diagnosis of gastric diseases, especially GC, and usefulness for predicting the prognosis.

BackgroundPostoperative recurrence impedes the curability of early-stage hepatocellular carcinoma (E-HCC). We aimed to establish a novel recurrence-related pathological prognosticator with artificial intelligence, and investigate the relationship between pathological features and the local immunological microenvironment.MethodsA total of 576 whole-slide images (WSIs) were collected from 547 patients with E-HCC in the Zhongshan cohort, which was randomly divided into a training cohort and a validation cohort. The external validation cohort comprised 147 Tumor Node Metastasis (TNM) stage I patients from The Cancer Genome Atlas (TCGA) database. Six types of HCC tissues were identified by a weakly supervised convolutional neural network. A recurrence-related histological score (HS) was constructed and validated. The correlation between immune microenvironment and HS was evaluated through extensive immunohistochemical data.ResultsThe overall classification accuracy of HCC tissues was 94.17%. The C-indexes of HS in the training, validation and TCGA cohorts were 0.804, 0.739 and 0.708, respectively. Multivariate analysis showed that the HS (HR= 4.05, 95% CI: 3.40-4.84) was an independent predictor for recurrence-free survival. Patients in HS high-risk group had elevated preoperative alpha-fetoprotein levels, poorer tumor differentiation and a higher proportion of microvascular invasion. The immunohistochemistry data linked the HS to local immune cell infiltration. HS was positively correlated with the expression level of peritumoral CD14+ cells (p= 0.013), and negatively with the intratumoral CD8+ cells (p< 0.001).ConclusionsThe study established a novel histological score that predicted short-term and long-term recurrence for E-HCCs using deep learning, which could facilitate clinical decision making in recurrence prediction and management.